Python SDK

The Python SDK auto-instruments supported LLM clients so you don't have to wrap each call.

Getting started

1. Install

uv add revenuetrack openai

2. Set environment variables

export REVENUETRACK_API_KEY=rt_...
export OPENAI_API_KEY=sk-...

3. Run a minimal OpenAI example

import os

from openai import OpenAI

import revenuetrack as rt

rt.init()  # reads REVENUETRACK_API_KEY

client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])

resp = client.responses.create(
    model=os.getenv("OPENAI_MODEL", "gpt-4o-mini"),
    input=[
        {"role": "system", "content": "Answer concisely."},
        {"role": "user", "content": "Explain coding like I am 5"},
    ],
)

print("LLM response:", resp.output_text)

The SDK captures usage and sends it to RevenueTrack in the background. Events are auto-flushed on process exit.

Supported providers

• OpenAI
• Anthropic
• Groq
• Google Gemini